English
Related papers

Related papers: Fast-dLLM: Training-free Acceleration of Diffusion…

200 papers

We present significant extensions to diffusion-based sequence generation models, blurring the line with autoregressive language models. We introduce hyperschedules, which assign distinct noise schedules to individual token positions,…

Machine Learning · Computer Science 2025-10-08 Nima Fathi , Torsten Scholak , Pierre-André Noël

Distributed LLM serving is costly and often underutilizes hardware accelerators due to three key challenges: bubbles in pipeline-parallel deployments caused by the bimodal latency of prompt and token processing, GPU memory overprovisioning,…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-03-05 Foteini Strati , Sara Mcallister , Amar Phanishayee , Jakub Tarnawski , Ana Klimovic

Unlike autoregressive language models, which terminate variable-length generation upon predicting an End-of-Sequence (EoS) token, Diffusion Language Models (DLMs) operate over a fixed maximum-length context window for a predetermined number…

Computation and Language · Computer Science 2026-03-09 Vittorio Rossi , Giacomo Cirò , Davide Beltrame , Luca Gandolfi , Paul Röttger , Dirk Hovy

Generative large language models (LLMs) have revolutionized multiple domains. Modern LLMs predominantly rely on an autoregressive decoding strategy, which generates output tokens sequentially and employs a key-value cache (KV cache) to…

Cryptography and Security · Computer Science 2026-02-13 Ye Yu , Yifan Zhou , Yi Chen , Pedro Soto , Wenjie Xiong , Meng Li

The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-03-24 Yichun Xu , Navjot K. Khaira , Tejinder Singh

Large Language Models (LLMs) excel in natural language processing tasks but pose significant computational and memory challenges for edge deployment due to their intensive resource demands. This work addresses the efficiency of LLM…

Hardware Architecture · Computer Science 2025-07-02 Zhican Wang , Hongxiang Fan , Haroon Waris , Gang Wang , Zhenyu Li , Jianfei Jiang , Yanan Sun , Guanghui He

Rapid advances in Large Language Models (LLMs) have spurred demand for processing extended context sequences in contemporary applications. However, this progress faces two challenges: performance degradation due to sequence lengths…

Computation and Language · Computer Science 2025-10-10 Wei Wu , Zhuoshi Pan , Chao Wang , Liyi Chen , Yunchu Bai , Tianfu Wang , Kun Fu , Zheng Wang , Hui Xiong

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…

Machine Learning · Computer Science 2026-04-20 Chuangtao Chen , Grace Li Zhang , Xunzhao Yin , Cheng Zhuo , Bing Li , Ulf Schlichtmann

Large language models (LLMs) demonstrate remarkable capabilities but face substantial serving costs due to their high memory demands, with the key-value (KV) cache being a primary bottleneck. State-of-the-art KV cache compression…

Machine Learning · Computer Science 2025-09-03 Yanqi Zhang , Yuwei Hu , Runyuan Zhao , John C. S. Lui , Haibo Chen

Diffusion Language Models (dLLMs) have garnered significant attention for their potential in highly parallel processing. The parallel capabilities of existing dLLMs stem from the assumption of conditional independence at high confidence…

Machine Learning · Computer Science 2026-05-13 Haohui Zhang , Zhiye Wang , Xiaoying Gan , Xinbing Wang , Bo Jiang

Diffusion language models offer unique benefits over autoregressive models due to their potential for parallelized generation and controllability, yet they lag in likelihood modeling and are limited to fixed-length generation. In this work,…

While diffusion Multimodal Large Language Models (dMLLMs) have recently achieved remarkable strides in multimodal generation, the development of interpretability mechanisms has lagged behind their architectural evolution. Unlike traditional…

Artificial Intelligence · Computer Science 2026-04-14 Haomin Zuo , Yidi Li , Luoxiao Yang , Xiaofeng Zhang

In this paper, we presents a novel method for improving text-to-image generation by combining Large Language Models (LLMs) with diffusion models, a hybrid approach aimed at achieving both higher quality and efficiency in image synthesis…

Computation and Language · Computer Science 2025-02-04 Julian Perry , Frank Sanders , Carter Scott

Diffusion models have achieved remarkable success in image and video generation. However, their inherently multiple step inference process imposes substantial computational overhead, hindering real-world deployment. Accelerating diffusion…

Computer Vision and Pattern Recognition · Computer Science 2026-01-07 Jiajun jiao , Haowei Zhu , Puyuan Yang , Jianghui Wang , Ji Liu , Ziqiong Liu , Dong Li , Yuejian Fang , Junhai Yong , Bin Wang , Emad Barsoum

Diffusion Large Language Models (DLLMs) promise fast non-autoregressive inference but suffer a severe quality-speed trade-off in parallel decoding. This stems from the ''combinatorial contradiction'' phenomenon, where parallel tokens form…

Computation and Language · Computer Science 2026-02-27 Yushi Ye , Feng Hong , Huangjie Zheng , Xu Chen , Zhiyong Chen , Yanfeng Wang , Jiangchao Yao

KV cache restoration has emerged as a dominant bottleneck in serving long-context LLM workloads, including multi-turn conversations, retrieval-augmented generation, and agentic pipelines. Existing approaches treat restoration as a…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-29 Sean Nian , Jiahao Fang , Qilong Feng , Zhiyu Wu , Fan Lai

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy…

Computation and Language · Computer Science 2025-12-03 Kecheng Chen , Ziru Liu , Xijia Tao , Hui Liu , Xinyu Fu , Suiyun Zhang , Dandan Tu , Lingpeng Kong , Rui Liu , Haoliang Li

Diffusion Language Models (DLMs) present a compelling alternative to autoregressive models, offering flexible, any-order infilling without specialized prompting design. However, their practical utility is blocked by a critical limitation:…

Computation and Language · Computer Science 2026-02-03 Zirui Wu , Lin Zheng , Zhihui Xie , Jiacheng Ye , Jiahui Gao , Shansan Gong , Yansong Feng , Zhenguo Li , Wei Bi , Guorui Zhou , Lingpeng Kong

Autoregressive Large Language Models (AR-LLMs) are widely used in software engineering (SE) but face limitations in processing code structure information and suffer from high inference latency. Diffusion LLMs (DLLMs) offer a promising…

Software Engineering · Computer Science 2025-10-07 Jingyao Zhang , Tianlin Li , Xiaoyu Zhang , Qiang Hu , Bin Shi

A critical approach for efficiently deploying computationally demanding large language models (LLMs) is Key-Value (KV) caching. The KV cache stores key-value states of previously generated tokens, significantly reducing the need for…

Computation and Language · Computer Science 2024-09-10 Akide Liu , Jing Liu , Zizheng Pan , Yefei He , Gholamreza Haffari , Bohan Zhuang